Monocular Road Detection Using Structured Random Forest

Abstract

Road detection is a key task for autonomous land vehicles. Monocular vision-based road-detection algorithms are mostly based on machine learning approaches and are usually cast as classification problems. However, the pixelwise classifiers are faced with the ambiguity caused by changes in road appearance, illumination and weather. An effective way to reduce the ambiguity is to model the contextual information with structured learning and prediction. Currently, the widely used structured prediction model in road detection is the Markov random field or conditional random field. However, the random fieldbased methods require additional complex optimization after pixel-wise classification, making them unsuitable for real-time applications. In this paper, we present a structured random forest-based road-detection algorithm which is capable of modelling the contextual information efficiently. By mapping the structured label space to a discrete label space, the test function of each split node can be trained in a similar way to that of the classical random forests. Structured random forests make use of the contextual information of image patches as well as the structural information of the labels to get more consistent results. Besides this benefit, by predicting a batch of pixels in a single classification, the structured random forest-based road detection can be much more efficient than the conventional pixel-wise random forest. Experimental results tested on the KITTI-ROAD dataset and data collected in typical unstructured environments show that structured random forest-based road detection outperforms the classical pixel-wise random forest both in accuracy and efficiency.

Fusing Appearance and Prior Cues for Road Detection

“…Furthermore, considering that one third of the upper part of the input images are not likely to contain any road area, and we can remove it as [25] suggested. In contrast to our proposed algorithm, the computational cost of the other state-of-the-art methods mentioned above are as follows: SRF [6] takes about 0.2 s with C++ code using a CPU @ 2.5 GHz; CN [7] takes about 2 s with C++ code using a CPU @ 2.5 GHz; FCN-LC [12] takes about 0.03 s with Python code using an additional GPU Titan X; BM [24] takes about 2 s with MATLAB code using 2 CPU @ 2.5 GHz; ANN [27] takes about 3 s with C++ code using a CPU @ 3.0 GHz; LidarHisto [29] takes about 0.1 s with C++ code using a CPU @ 2.5 GHz.…”

“…Additionally, some other recently developed state-of-the-art methods which show excellent performance and rank high on the KITTI road benchmark are used for the purpose of comparison. These algorithms include SRF [6], CN [7], FCN-LC [12], BM [24], ANN [27] and LidarHisto [29].…”

“…Chacra et al [4,5] trained a support vector machine (SVM) classifier on thousands of annotated images and then used it to classify the extracted features as either road surface or non-road surface. Xiao, L et al [6] presented a structured random forest based road detection algorithm which can model the contextual information efficiently to classify road pixels. The algorithm outperforms the classical pixel-wise random forest based methods both in accuracy and efficiency.…”

Gaussian process regression-based robust free space detection for autonomous vehicle by 3-D point cloud and 2-D appearance information fusion

“…Kühnl et al 19 proposed an approach based on the computation of spatial ray features which generates many rays in several directions of each base point and applies trained classifier on the accumulated ray features to detect the lanes and road. Xiao et al [20][21][22] use boosted trees to train the road model and fuse the color and Lidar information into the conditional random field to obtain a coincident result. Deep learning-based methods 23 have achieved nearly a perfect result that relies on powerful deep network architectures which shows that for certain scenes, the models can be well learned but it is not sure that the models can be transferred in other unseen environment without retraining.…”

A fast calibration approach for onboard LiDAR-camera systems

“…Lots of algorithms for calibration between camera and LiDAR have emerged in decades. [9][10][11][12] The core task of calibration is to build the relationship between 2-D points on the image and 3-D points on the point cloud. However, manually establishing correspondences for their mapping relationship is laborious and inaccurate because it requires multiple matches.…”